I am a Strange Dataset: Metalinguistic Tests for Language Models Paper β’ 2401.05300 β’ Published Jan 10, 2024 β’ 3
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality Paper β’ 2204.03162 β’ Published Apr 7, 2022 β’ 1
Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language Paper β’ 2306.16410 β’ Published Jun 28, 2023 β’ 28
Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants Paper β’ 2112.09062 β’ Published Dec 16, 2021
Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks Paper β’ 2204.01906 β’ Published Apr 5, 2022
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset Paper β’ 2303.03915 β’ Published Mar 7, 2023 β’ 7
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model Paper β’ 2211.05100 β’ Published Nov 9, 2022 β’ 32